Papers

Speech-based Alzheimer's disease (AD) detection increasingly relies on speech-enhanced and curated versions of the Pitt Corpus, where speech enhancement, sample selection, and demographic balancing are often treated as beneficial preprocessing steps. However, whether these transformations improve real-world AD detection or instead affect model generalization and prediction behavior remains unclear. In this work, we revisit the role of speech preprocessing and dataset curation across widely used benchmarks for speech-based AD detection. We evaluate the speech quality of different datasets, the cross-dataset generalization of multiple deep learning models under matched and mismatched enhancement settings, and the behavior of several recent large audio-language models (LALMs). Experimental results show that across multiple supervised speech models, speech-enhanced datasets often improve in-domain performance while reducing robustness in cross-domain evaluation. Matched enhancement between training and test data alleviates, but does not eliminate, this degradation. LALMs show a similar sensitivity: enhanced datasets induce stronger class imbalance and prediction shifts than unprocessed data. These results suggest that speech preprocessing and dataset curation can substantially influence downstream AD detection behavior, indicating that “cleaner” speech datasets are not necessarily more reliable for real-world AD detection.

Fleets of LLM agents now externalize effects that cannot be fully undone: they move money, deploy code, delete data, and disclose information. Current controls check one effect at a time, so a fleet of individually authorized agents can overdraw its principal's risk under a shared trigger while every local gate stays correct. We propose the irreversibility budget, a cumulative account of residual value-at-risk that a trusted runtime maintains for each principal across agents, workflows, and tenants. Treating irreversibility as a first-class resource, the runtime charges each effect its residual loss below the agent and denies the marginal effect once the aggregate would overdraw the budget. Getting the price right is hard, because effects are heterogeneous, adversarially declared, and correlated. We perform a controlled study in which per-effect gates admit fleet-level overdraws of up to 48 times the tenant's risk limit while the budget holds every correctly charged run within that limit. Conservative, dependency-aware pricing remains the central open problem for a deployable design.

Two-sided service marketplaces are moving from deterministic request-form intake to AI-native probabilistic matching, enabled by large language models (LLMs) that infer intent, preferences, and latent constraints from natural language. Relying on inferred intent rather than fixed-form fields forces these platforms to regenerate the provider-side preference taxonomy underwriting matching, search, and pricing: attributes interpretable to service providers while remaining a useful signal for marketplace decisions. We present an autoresearch loop that generates this taxonomy, one occupation at a time, and has been deployed in production at a major U.S. consumer services marketplace since April 2026, spanning 132 occupations. Instead of one global hierarchy, the loop treats each occupation as an independent generation problem and runs iterative propose-evaluate-keep refinement cycles. Each candidate tag set is scored by a recalibrated six-rubric LLM-as-judge framework, and a 7-critic panel of distinct personas contributes weighted penalties to an adjusted score, with no hard vetoes. A separate parity-mapping stage maps legacy request-form Q&A pairs back to the generated taxonomy, yielding both a coverage signal and an interface for human quality assurance; it does so by first inferring the provider attribute each legacy question was meant to measure, rather than translating questions to tags literally.

Modern data systems are commonly studied through computational and information-theoretic methods, while their algebraic properties remain largely unexplored. This paper introduces a mathematical framework for modelling data systems using algebraic codes over finite groups, organized by an axiom signature: each algebraic axiom of the data domain is shown to be sufficient for a specific coding-theoretic capability, and each implication is given its precise reading (MDS parameters do not require a field; quotients require normality, not commutativity). Three types of results are presented. Proved: a Gilbert-Varshamov existence bound over arbitrary finite groups, commutative or not; explicit direct-sum codes over the elementary divisors of any finite abelian group; that transactions preserving a validity predicate form a submonoid of the full transformation monoid, which is not a group; that schema-preserving transformations form a finite group whose orbits are counted by Burnside's lemma; and that the constraint-preserving bijections of a data system form a finite group whose orbits partition the valid configurations. Demonstrated: an explicit code construction over $\mathbb{F}_5$, with known codes over $\mathbb{Z}_4$ and $(2^U,\triangle)$ cited to situate the framework. Proposed: an encoding efficiency measure Ef and an optimization functional $\Phi$ with tunable weights, both evaluated at declared coding instances. Weight-independent comparison holds under componentwise dominance; in general the weight simplex decomposes into polyhedral chambers on which the induced order is constant.

Most advances in keypoint descriptions address monomodal settings, where image variations arise from viewpoint, illumination, or contrast changes. Multimodal scenarios involve images produced by fundamentally different sensing processes, such as multispectral imaging, RGB-depth, satellite imagery, or medical imaging, causing the same structures to appear differently. A common solution to cross-modal description is to train descriptors for each modality pair, which requires retraining whenever the modalities change, or to train large models, which incur a significant increase in runtime. Instead, we propose CrossFeat, a framework that enables an existing monomodal descriptor to operate across modalities. Our method learns a crossing function in descriptor space that maps features from one modality to a representation compatible with another. To preserve the structural information captured by the original descriptor, CrossFeat introduces a geometry-appearance disentanglement such that only appearance is altered while the geometric properties are preserved. Experiments across multiple domains and datasets demonstrate improved performance in multimodal matching.

Autonomous LLM agents increasingly act on a user's behalf: they hold credentials, call tools and services, and spawn sub-agents that act further on their behalf. This turns a long-standing distributed-systems question – who is authorized to do what, on whose authority – into an urgent and largely unsolved problem, because the component driving each agent is a language model an adversary can hijack. We argue that agent security must be evaluated under an untrusted-model assumption: a correct system is one in which a fully prompt-injected agent still cannot exceed the authority explicitly delegated to it. Against this standard we make three contributions. First, we give a threat model for multi-agent delegation centered on four adversaries – confused deputy, token theft and replay, prompt-injection privilege escalation, and compromised sub-agents – and derive eight security requirements a governed agent system must meet. Second, we show the gap is real: a default agent runtime modeling common practice (broad bearer credentials, authorization gated inside the model) fails all four threats, and across four widely used frameworks – LangGraph, CrewAI, AutoGen, and the Model Context Protocol (MCP) authorization model – three provide no built-in confinement and one only partial; no existing standard alone covers the requirement set. Third, we implement and adversarially evaluate an authorization broker that closes the gap. It blocks all four threats; it resists 11 direct attacks on its design and accepts 0 of 200,000 forged tokens; it confines a compromised sub-agent to its delegated task (a mean of 1.5 reachable actions versus all 8,100 under bearer delegation, across 2,000 randomized scenarios); and it enforces at microsecond cost (about 2.6 microseconds per decision), negligible against model inference. These principles are also realized in production in VotalAI's LLM Shield.

Chain-of-thought monitoring is proposed for AI oversight, yet evaluations often provide monitors with a trusted reference answer. We ask whether answer access improves verification of the reasoning or mainly supplies information about its conclusion. We collected 237 naturally generated, step-numbered solutions to 79 Humanity's Last Exam physics questions and independently labelled final-answer correctness and the first false step. Eight LLM monitors evaluated the traces with varying access to the reference answer. Certification raised mean balanced accuracy from 0.637 to 0.796, but its effect on error detection depended strongly on the conclusion: recall increased by +0.299 on wrong-answer traces, while there was no evidence of improvement on correct-answer traces containing a reasoning error (-0.083, 95% CI [-0.196, +0.030]). We then held the reasoning trace fixed in a seven-monitor certificate-congruence intervention. Replacing the true certificate with the trace's own incorrect conclusion reduced flagging by 0.659 (95% CI [0.602, 0.711]) and left flagging 0.389 below the answer-blind level. Conversely, a conflicting false certificate increased flagging of clean traces by 0.580, with 82.9% of newly flagged cases assigning the alleged error to an interior reasoning step. Trusted-answer access can therefore make monitoring appear substantially stronger because aggregate performance combines independent reasoning verification with a powerful certificate-conclusion consistency signal.

We propose a novel approach to learning-based attack forensics called DUPIN. DUPIN performs unsupervised pre-training on an enormous amount of audit events in the form of provenance graphs. It then proceeds to a few-shot learning stage, leveraging a small number of labeled attack examples to fine-tune its detection capabilities. We pretrain DUPIN on up to 38 - 52 days of audit logs (7.3TB total) and evaluate it against various baselines on 25 APT campaigns across four different data sources, facilitating the scalable evaluation.

LLM-based diagnostic systems achieve high semantic accuracy on benchmarks, but open-ended evaluation on clinically uncommon presentations reveals a systematic gap between headline accuracy and verifiable clinical reliability. We evaluate an LLM+rare-disease-RAG pipeline across two cohorts and show that the paradigm produces confident outputs that are frequently unverifiable and systematically resistant to clinician interrogation. We present NSIDDx (Neuro-Symbolic Integrated Differential Diagnosis System), a design framework arguing that DDx systems in low-resource settings must treat the clinician as an active reasoning agent. We instantiate this through a neuro-symbolic pipeline with ternary symptom encoding, contradiction detection, audit strings, and practitioner override - running offline on consumer hardware. We distill five design principles for clinician-in-the-loop clinical NLP and invite the prospective studies needed to validate the claim at scale.

Context: Software engineering is moving from AI-assisted practices like vibe coding, in which assistants accelerate individual developers, towards Agentic Software Engineering (ASE), in which autonomous agents are delegated goal-level tasks. However, industry reports a productivity paradox: as individual productivity increases, team throughput, review capacity, and stability degrade because team-scale software engineering discipline is neglected. Objective: This paper aims to establish the conceptual and methodological foundations of Spec-Driven Development (SDD) as an enabling discipline for ASE at team scale and characterize the harness, i.e., the technical and methodological mechanisms through which teams govern agent behavior. Method: We conducted a conceptual analysis drawing predominantly on gray literature, including ASE vision and roadmap papers, practitioner reports, talks, and tooling, because peer-reviewed evidence and a shared academic-industrial vocabulary are not yet established. Results: Using a comparative characterization of the paradigm progression as conceptual framing, the article presents (i) a socio-technical model of SDD in which specifications act as the contract substrate between humans and agents; (ii) an operational characterization of the harness, distinguishing the technical harness around the agent from the methodological harness around the team, with worked examples; and (iii) a typology of five human–agent interaction patterns through which the human role is redefined. Conclusion: We conclude that SDD reconstitutes, in specification-centric form, the contracts that vibe coding dissolves: accountability, verifiability, and transferability. Given the immaturity of the evidence base, this work is presented as a first step toward academic-industrial consensus rather than a validated theory, and outlines a research agenda for future empirical validation.

As people increasingly interact with LLM assistants in daily life, continually adapting to individual preferences has become essential for effective long-term interactions. However, user preferences are rarely stated in full, and instead emerge through heterogeneous, latent, and noisy signals, with existing methods relying on raw interaction histories or costly reward-based optimization to manage personalization. We introduce HypReflect, a reliable, scalable framework for continual personalization that infers explicit, uncertainty-aware preference hypotheses from diverse user signals, reflectively refines them as new evidence accumulates, and incorporates the resulting user model through hypotheses-guided self-distillation. Experiments across three personalization settings: online personalization, multi-session interactions, and implicit behavioral signals, show that HypReflect outperforms a range of baselines, including raw-history and incremental-update methods. We further demonstrate strong generalization to unseen users and cross-domain settings, along with stability across context budgets, reusable hypotheses, and more focused personalization. These results suggest a step towards reliable and scalable continual personalization through explicit, revisable user preference hypotheses.

Many people now see AI systems as not just productivity tools but as social companions. Researchers are eager to study the consequences of AI companionship behaviors, such as validation, which evoke trust, empathy, and attachment in human-human interaction. However, human-AI interaction data is limited and unreliable, slowing research progress. We scale small amounts of real-world data by simulating multi-turn human-chatbot dialogue across a range of chatbot behaviors and use cases. We release CompanionSim: a simulation framework with 2,240 simulated human-chatbot conversations representing 16 chatbot behaviors across seven use cases. Human participants annotated the simulated conversations and real-world conversations in two experiments probing perceptions of companionship behaviors. We conducted Study 1 with a U.S. representative sample ($N_{1}~=~628$) and Study 2 across the U.S., U.K., India, and Nigeria ($N_{2}~=~3,646$). Surprisingly, we find that companionship behaviors reduced likability, humanlikeness, and trust in AI chatbots. These effects were larger in particular subgroups: women and older participants saw companionship chatbots as less likable, humanlike, and trustworthy. We encourage researchers to leverage real-world and synthetic data together to study the differential impacts of AI companions and to create benchmark evaluations of AI chatbots.

Large Language Models (LLMs) are increasingly used as conversational search engines for academic literature, yet whether they judge papers on content or on authority signals has not been tested causally. We investigate authority bias: systematic preference for papers based on author prestige, venue, and citations rather than content. Holding title and abstract constant, we vary authority metadata across three counterfactual conditions (original, flipped, boosted) over eight LLMs (five open-weight and three frontier closed-weight) in an in-context, single-turn, top-1 recommendation setting. Our experiments show that authority bias is substantial and directional, varies markedly across models, and is only partially addressable through prompt-level debiasing. We further document a say-do gap: debiasing instructions suppress authority mentions far faster than authority-driven flips, so surface auditing systematically underestimates behavioral bias.

While it is fairly well known how empirical software engineering (ESE) is used in the academic world, we have limited knowledge of how ESE is practiced in industry. As part of our regular column on empirical software engineering (ACM SIGSOFT SEN-ESE), we want to dedicate a series of articles to interviewing ESE practitioners from various companies. Among other things, we want to understand how ESE processes are implemented in industry, e.g., different research methods, how practitioners decide on what to study, how research results are used within companies and beyond, and if they face recurrent impediments to using ESE methods in industrial contexts. In the first edition of "ESE in Practice", we are joined by Ciera Jaspan and Collin Green from the Developer Intelligence team at Google. This article is a faithful account of our conversation from August 13, 2026, which we edited for our column.

Maintaining an abstraction of the execution history of threads can improve the precision of data race detection in static analysis. Here, we extend the digest framework to handle concurrency constructs and synchronization mechanisms that have been ignored in static race detection. We introduce mechanisms for the commonly used thread barriers, as well as pthread_once, which allows to ensure that an action is executed only once. We also instantiate the framework with an abstraction of locksets held by ancestor threads. We propose a suite of litmus tests to evaluate analyses for these features and compare our implementation to state-of-the-art tools, finding that they lack support.

LLM agents that cache recovery suggestions from API errors can skip re-derivation in later episodes, spending fewer tokens and fewer model calls on constraints they have already learned. Server-side data drift turns those cached fixes into silent failures, and the usual remedy, re-deriving on every episode, gives the savings back. We introduce invalidation contracts, a protocol layer that attaches version stamps and cacheability hints to every recovery suggestion so the client can evict stale entries without trial and error, and keep the rest. The contract decomposes realized savings into two independent factors: validity, the fraction of cached suggestions that remain correct after a drift event, and compliance, the fraction the planner applies on the first attempt. Validity depends only on the protocol and is vendor-independent. Compliance depends on the planner model: identical wire bytes yield 100% first-try compliance on Claude Haiku 4.5 and 11% or below on Claude Sonnet 5, which exhibits input-schema conservatism, refusing fixes that add fields the original request did not contain. We evaluate across seven models, three serving paths, two domains, and approximately 9,400 episodes. Row-level invalidation raises compliance by 0 to 66.7 percentage points across the seven models, 55.6 to 66.7 on three, and recovers 29-33% of baseline token cost on four of seven models, while table-level invalidation destroys co-located entries and drops post-drift first-try rates to 0% on five of seven. Eviction precision is 1.00 at row granularity on every model under the row-level oracle of Section 4.1. The contract adds 15% to response payload. Version-stamp validity is deterministic by construction and produced identical results across every model and serving path, with zero contract failures in the entire evaluation.

Long-tail autonomous driving failures are often framed as rare-object recognition errors. We argue that this view is incomplete: the decision-critical question is not only whether a model recognizes an unusual object, but whether it infers how that object changes the ego vehicle's feasible high-level actions. We formalize this problem as decision-level driving affordance prediction, where a model maps a front-view image, ego-motion history, and navigation command to a structured longitudinal–lateral meta-action. To evaluate this capability, we introduce CoLT-Drive, a 3,536-sample counterfactual long-tail benchmark that inserts rare objects into otherwise fixed driving scenes and measures whether models predict acceptable action pairs. To improve deployable small VLMs, we propose KPA, a knowledge-preserving adaptation framework that combines structured perception-to-decision prompting, SLERP-based expert merging, and RegMoE, a regime-aware LoRA mixture-of-experts module. KPA preserves the pretrained model's open-world knowledge while allocating lightweight adaptation capacity to different driving decision regimes. Experiments on an in-domain driving split and CoLT-Drive show that KPA achieves 60.8% pair accuracy on CoLT-Drive, outperforming the pretrained Qwen3-VL-2B baseline (50.3%) and LoRA SFT (32.4%) while maintaining competitive in-domain accuracy. Our benchmark and code are available at https://huggingface.co/datasets/tangzx2024/CoLT-Drive and https://github.com/tangzhengxu/CoLT-Drive.

Long documents often distribute important information across extensive narrative passages and multiple tables, making faithful summarization particularly challenging. Existing methods may generate individually supported quantitative facts and analytical statements yet associate them incorrectly, producing quantitatively plausible yet analytically unfaithful summaries. In this work, we propose LOOMSUM, a training-free framework that extracts source-grounded atomic evidence, explicitly links table-derived facts with supporting narrative analyses, and plans the discourse structure before generation. We also introduce Table-Grounded Faithfulness (TGF), a claim-level metric that separately evaluates Numeric Grounding, Analysis Support, and Relation Consistency. Experiments on the text–table summarization benchmarks FINDSum and USTT show that LOOMSUM improves analytical faithfulness while maintaining strong summarization quality. Human evaluation finds positive component-level associations with the corresponding human judgments. Our Relation Consistency metric further shows stronger agreement with human relation judgments than generic factuality metrics, indicating that explicit cross-modal linking helps reduce errors in which supported quantities are paired with incorrect narrative interpretations. Together, these findings show that faithful long text–table summarization requires not only grounding individual facts, but also preserving the relations between them.

We prove Friedgut's conjecture (J. Amer. Math. Soc. 12 (1999)) that every increasing family in the $p$-biased discrete cube with bounded relative boundary can be approximated arbitrarily well by one whose minimal elements have size bounded independently of the dimension and the bias. For $0<p\le 1/2$, every increasing Boolean function with total resampling influence at most $K$ is $\varepsilon$-close under $\mu_p^n$ to a monotone DNF of width $\exp(O((K+1)^2/\varepsilon^2))$, from which the full conjecture follows for all $p\in(0,1)$. We build on Hatami's pseudo-junta theorem (Ann. of Math. 176 (2012)), whose approximator need not be increasing. Our randomized shifts produce an increasing approximator that is measurable with respect to a controlled refinement of Hatami's adaptive partition. Retaining only short positive certificates yields the desired narrow DNF.

The separation of cardiovascular sounds is a critical task in biomedical signal processing. In this paper, we introduce XVAE-WMT1, an unsupervised explainable generative AI algorithm combining a variational autoencoder (VAE) with explainable AI (XAI), wavelet-based inputs, a post-hoc output mask, and temporal consistency (TC) loss. Unlike existing supervised and VAE-based methods that rely on Short-Time Fourier Transform (STFT) and ignore latent interpretability, XVAE-WMT requires no paired clean recordings and integrates a Continuous Wavelet Transform (CWT) front-end for superior time-frequency localization. We assessed the latent space interpretability via different metrics, with SHAP (SHapley Additive exPlanations) enabling dimensionality reduction to the top 75% of latent features while preserving separation quality. Evaluated across two datasets using Signal-to-Distortion Ratio (SDR), Signal-to-Interference Ratio (SIR), and Signal-to-Artifacts Ratio (SAR), XVAE-WMT attains 26.8 dB SDR, 32.8 dB SIR, and 28.6 dB SAR.

Large language model (LLM)-based multi-agent systems tackle complex reasoning by orchestrating how multiple agents are configured and how they collaborate. A central challenge is to adapt orchestration to the evolving collaboration state. Routing from the query alone cannot adapt to intermediate progress or errors, which hurts accuracy. Routing from the complete execution history supplies this missing context, but forces later decisions to process every prior step, including redundant or low-utility ones. This creates an execution-history overload that inflates cost. Effective orchestration instead requires a compact state that captures useful progress without accumulating redundant context. We propose Gated-Memory Routing, which conditions each decision on the query and a learned execution memory. A learned Memory Write Gate commits only non-redundant reasoning steps, and a learned Retrieval Gate supplies each agent a compact, relevant subset, so every decision conditions on a clean, informative state. At each step, the system selects the next role and backbone from this memory, while an Adaptive Halting Controller stops execution once the memory contains sufficient evidence for answering. Across five reasoning and code-generation benchmarks, our framework is both effective and efficient: it attains the best average accuracy, exceeding the strongest baseline by 2.44 points, while reducing HumanEval inference cost by 31.9% relative to that baseline. Code is available at https://github.com/rajibrhasan/gated-memory-routing

In this work we propose an approach to construct a fully asynchronous unsourced random access communications (URA) system. Besides the common URA features such as the absence of the user identification information in the packet and the decoding oriented to receiving the content of the messages, there is no limitation on the user transmission timing. The active users can transmit their packet any time on demand. The proposed system belongs to the class of preamble-payload URA formats. Contrary to the typical role of the preamble to serve as a temporary user identification, the preamble serves for the purpose of timing acquisition. The proposed system also employs a very small pool of preambles to resolve collisions of packets transmitted simultaneously.We provide a performance analysis and simulation results for the proposed system and demonstrate that for a wide range of signal-to-noise ratios (SNR)s the supported numbers of active users are close to the numbers of users supported by a slotted URA system counterpart.

Multimodal Large Language Models (MLLMs) have achieved strong performance on OCR-centric document understanding and text-rich visual reasoning benchmarks. Yet existing evaluations largely assume that every task is valid and answerable. In real-world OCR scenarios, this assumption often fails: questions may rely on illegible text, occluded evidence, nonexistent visual targets, contradictory premises, or missing variables. We study this reliability gap as OCR-grounded Task Verification: before answering, a model should determine whether the Image Premise (IP), Textual Premise (TP), and Question (Q) jointly define an executable task. We introduce VeriOCRBench, a 1,800-sample human-verified benchmark built from source images drawn from 8 OCR-related datasets and spanning 8 real-world image domains, with controlled, image-grounded diagnostic tasks. It contains 1,600 trap-injected invalid tasks across 8 trap types and four verification dimensions—Visual, Contextual, Factual, and Logical—plus 200 trap-free controls for measuring over-refusal. Built with a Visual Atomic Fact (VAF)-anchored pipeline and full human auditing, VeriOCRBench enables decoupled evaluation of task verification, root-cause diagnosis, and over-refusal. Evaluating 15 leading MLLMs reveals persistent blind compliance, diagnosis failures, and prompt-induced over-refusal, exposing a critical reliability gap in current OCR reasoning systems. The code is available at: https://github.com/zy001122/Beyond-Blind-Compliance.

Existing research on object hallucination in multimodal large language models (MLLMs) predominantly attributes the problem to language priors such as over-reliance on textual co-occurrence statistics. We challenge this view by presenting quantitative evidence for a complementary, under-explored cause: visual-origin hallucination, where hallucinations arise from incorrect visual feature extraction and misalignment between image and text embeddings. Through cosine similarity analysis and Smooth Grad-CAM entropy measurements, we show that hallucinated samples exhibit systematically lower image-text similarity (average 0.158 vs. -0.122) and inverted attention patterns, where attention is dispersed when the target object is present but wrongly concentrated when it is absent. Guided by this diagnosis, we propose Adversarial Contrastive Fine-Tuning (ACFT). ACFT uses an Adversarial Hallucination Attribute Flipping (AHAF) procedure, involving minimal, targeted adversarial perturbations that flip an image's hallucination attribute, to construct perfectly aligned positive-negative pairs, which are then used for contrastive fine-tuning. AHAF simultaneously serves as a diagnostic probe, revealing that MLLM visual representations lie dangerously close to hallucination decision boundaries. Requiring only 0.9% of the COCO dataset and adding zero inference overhead, ACFT achieves state-of-the-art performance on POPE, MME, and four description-level hallucination benchmarks across LLaVA, MiniGPT-4, and Qwen2.5-VL. Code is available at https://github.com/zxp555/ACFT_MM

Scientific domain entity linking (EL) differs from general domain EL because mentions and entity names often lack lexical overlap. Another challenge is that specialized terminology is used in the scientific domain, which is rarely encountered in models pretrained on general domains. Therefore, models trained on general domains transfer poorly to scientific domains. To address this, in-domain fine-tuning is the natural remedy. However, many scientific domains lack expert-annotated data, motivating the need for a zero-human-annotation approach. Existing zero-shot methods heavily rely on LLMs to generate aliases across entire mention corpora, which incurs substantial computational cost, and those methods provide no mechanism to filter out noise from LLMs. To address these challenges, we propose Sci-ZSEL, a framework that selectively generates entity aliases with an LLM to control computational cost, and applies an ontology-aware filter to remove aliases that semantically drift toward ontology neighbors. Then, filtered aliases are used to construct pseudo-labeled mention-entity pairs for fine-tuning. To enable evaluation of EL under low lexical overlap, we also release a new animal science EL benchmark linked to three livestock trait ontologies, where mentions and entities exhibit substantially lower lexical overlap than in existing benchmarks. Across five benchmarks, Sci-ZSEL outperforms the non-fine-tuned baseline, is most useful on nonoverlapping mentions, and combining it with curated synonyms gives the best performance in most settings.

LLM agents increasingly diagnose incidents and propose remediations. In a GitOps workflow, applying a fix means editing a version-controlled config file, and the obvious implementation, having the model author the edited file or a diff, is what practitioners reach for first. Evaluating that choice on real Kubernetes manifests, we find no text-generation strategy is safe for unattended automation. Unified diffs are unsafe: under strict patching almost none apply, but that is an artifact, since a tolerant tool (GNU patch) applies 96%, yet silently misapplies about 1 in 7 (14-20%) with no error signal. Full-file rewrite is capability-dependent: a small model corrupts the file, while a frontier model is usually correct but non-deterministic (it silently drops a field or edits a neighbor on some runs) and must regenerate the whole file, costing O(file size) per edit. We present an alternative that separates the semantic decision (which resource, field, and value) from the syntactic act of editing the file. The agent emits only a structured field-change intent; a deterministic pipeline indexes manifests by (kind, name), locates the target scalar's exact character span via the YAML parser's node position marks, and replaces only that span in the raw text. Because the file is never re-serialized, the diff is minimal by construction, formatting and comments are preserved, and the edit is correct and deterministic independent of the model, at O(1) generation cost. The contribution is the pairing of an LLM-proposed intent with a deterministic, fail-closed application contract for GitOps. We implement it in KubeAstra (Apache-2.0) and release the benchmark. Our claim is scoped to faithful application of a known change; whether the change is right is left to human PR review.

Automatic academic paper-to-slide generation is inherently iterative, because creating an effective presentation requires repeated cycles of generation, critique, and revision. Recent multi-agent systems partially acknowledge this through internal critique-and-revise loops, while conversational approaches allow users to refine generated slide decks through dialog. However, these refinement processes either remain largely closed to the user or introduce feedback only after a complete deck has been produced, limiting the user's ability to participate in the iterative refinement of narrative flow, content allocation, and presentation emphasis. To address this gap, we introduce ConvDeck, a multi-agent pipeline for conversational paper-to-slide generation that distributes interaction across the pipeline through stage-specific loops, allowing users to iteratively refine both the presentation outline and the final slide deck at the stages where each kind of decision is made. These loops are driven by a refinement mechanism in which agents can think, speak, and act, enabling them to either directly apply edits or respond conversationally to clarify user feedback and discuss revision options. Our evaluation shows that stage-specific conversational feedback improves user-goal satisfaction while preserving narrative coherence, content quality, and visual presentation.

Weight-only post-training quantization (PTQ) can alleviate the computational burden of serving large language models (LLMs) at scale. However, existing PTQ methods often fail to generalize across models and suffer severe accuracy loss below 2 bits. Many leverage unstructured sparsity to mitigate this loss, but at the cost of regularity and GPU-friendly execution. We present QTEA, a sub-2-bit PTQ framework that quantizes weights into ternary values and uses salient weights as residual error compensators. To maintain hardware efficiency, residuals are assigned to selected columns with semi-structured $1:4$ sparsity within the salient columns. We further add column-wise rescale refinement to GPTQ-style column-by-column quantization, alternately updating per-column scales and ternary assignments to reduce reconstruction error. We also identify order-dependent error propagation in GPTQ and introduce error decay to attenuate late-stage error accumulation. On Qwen3-14B, QTEA compresses all weights to an effective 1.7 bits per weight while improving average accuracy over the strongest ternary PTQ baseline by 16.7%. It also achieves 1.40$\times$ and 2.61$\times$ lower perplexity on WikiText and C4 respectively. This trend holds on Llama3-8B, where QTEA obtains a 6.6% accuracy gain and 1.34$\times$ / 1.95$\times$ lower perplexity on the same datasets. Finally, we develop a lookup-table based kernel that achieves 7.2$\times$ faster per-token generation over an FP16 baseline. Code is available at https://github.com/Intelligent-Microsystems-Lab/QTEA.

Large language models (LLMs) are increasingly used as judges for subjective tasks, where annotators disagree and the relevant question is not only how accurate a judge is, but whose judgments it reproduces. Sociodemographic prompting conditions the judge on an annotator's demographic profile to align its judgments with the corresponding group's. We test whether this alignment emerges distributionally, comparing the predicted label distributions of 23 open-weight LLMs on three subjective tasks against those of real annotator groups, under three conditions: no demographic information, single-attribute profiles, and intersectional profiles over gender, age, race, and education. Three findings emerge. First, a judge prompted with no demographics is not perspective-neutral: models best reproduce the judgments of White, college-educated annotators. Second, demographic conditioning is asymmetric: it moves the judge toward majority groups and away from minority groups, most strongly on offensiveness, where intersectional profiles amplify the harm. Third, by comparing base and instruct models we identify instruction-tuning as a possible source of the asymmetry. Demographic conditioning should therefore be used with caution to estimate group judgments: conditioning moves predictions away from the reference distributions of the minority groups the method is often invoked to serve.

We classify Boolean Holant problems with a supplied binary disequality signature and an arbitrary fixed finite set of algebraic complex-valued signatures. Each problem is polynomial-time computable or $\#\mathsf{P}$-hard, and the tractability criterion is decidable. The proof combines arity reduction with the growth of the available binary transfer group and uses stable pairs to recover the structure of higher-arity signatures. We also prove a dichotomy for the disequality-edge model when the signature set contains an endpoint-nondegenerate irreducible eight-vertex signature, resolving the corresponding arity-four cases in the main proof.